 Chi McIsaacandMick Qian
|
6215aecd51
|
[diffusion] feat: add metrics support (#19084)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-18 13:22:03 +08:00 |
|
|
Khoa Pham
|
b98a2d1096
|
[Docs] GLM-5.3-Flash cookbook: temporarily remove the DCP option (#40036)
|
2026-09-17 16:17:25 -07:00 |
|
|
Arseniy Mironov
|
a1b4ec02ae
|
[NPU][Diffusion] FA MXFP8 and modelslim w4a4f8 and w8a8f8 support for Wan2.2 and FLUX (#39438)
|
2026-09-17 13:13:05 +03:00 |
|
|
yl3469andShuwen Wang
|
1a90ae6727
|
Add Agentic-Aware Tail-Optimized LRU eviction to the unified radix cache (#34012)
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
|
2026-09-17 17:52:59 +08:00 |
|
|
faceless voidandronnie_zheng
|
44bd359082
|
[NPU][Diffusion] Optimize SenseNova-U1 batched generation (#39382)
Signed-off-by: syd520zy <529477025@qq.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-09-17 10:08:20 +03:00 |
|
|
MickandMick Qian
|
c525ed8f02
|
[diffusion] fix: preserve explicit attention backends during autotune (#39882)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-17 13:28:55 +08:00 |
|
|
Liangsheng YinandBBuf
|
464fffbec8
|
dsv4.1: chat encoding and tool parsing (#39665)
Co-authored-by: BBuf <1182563586@qq.com>
|
2026-09-16 20:49:42 -07:00 |
|
|
Thomas Wang
|
f60652a43e
|
[AMD] Update deepseek-v4 PDI and cache policy setting for agentic workload (#39702)
|
2026-09-15 21:16:30 -07:00 |
|
|
jacky.chengandChangLiu0709
|
a9bb4d7d45
|
[AMD] Align Qwen3.5 MI355X HiCache cookbook with kernel / page_first (#39572)
Co-authored-by: ChangLiu0709 <cliu1004@amd.com>
|
2026-09-16 11:22:28 +08:00 |
|
|
amote-i
|
575163ff32
|
[NPU] [DOC] delete unsupported models in npu docs (#39555)
|
2026-09-15 14:55:17 +08:00 |
|
|
amote-i
|
bdf8886ad3
|
[NPU] [DOC] Rename NPU hardware to Ascend A2/A3 Series product (#39389)
|
2026-09-15 10:33:14 +08:00 |
|
|
|
a25f213bc4
|
[diffusion] docs: give the RTX 5090 its own H3 recipe, measured on a physical desktop (#39373)
Co-authored-by: Mick Qian <mickqian@radixark.ai>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-15 09:15:13 +08:00 |
|
|
ChangLiu0709
|
242d8a70c0
|
[AMD] GLM-5.2 MI355X MXFP4: bump image to 20260913, enable TOPK_V2 (#39406)
|
2026-09-14 21:50:52 +08:00 |
|
|
Theresa Shan
|
95140a7b0c
|
[docs] DeepSeek-V4: MI355X PD disaggregation recipes for all three strategies (#39396)
|
2026-09-14 02:11:51 -07:00 |
|
|
jacky.cheng
|
2f5cc8e33e
|
[AMD] Align Qwen3.5 MI355X cookbook with AttnFP8-V2 and HiCache direct / page_first_direct (#39358)
|
2026-09-14 12:46:17 +08:00 |
|
|
|
42b5af8c62
|
[diffusion] docs: refresh the VDN-H3 on b200 numbers in cookbook (#39244)
Co-authored-by: haochengxi <xihc@berkeley.edu>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
|
2026-09-14 11:50:40 +08:00 |
|
|
|
6220f45d8e
|
[PD] Add /v1/responses support to the HTTP PD router (#36141)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-09-13 22:48:13 +08:00 |
|
|
Shangming CaiandXinyuan Tong
|
14a131ad5b
|
[PD][OpenAI] Gate /v1/responses persistence behind --enable-response-store, default off (#39122)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-09-13 21:20:47 +08:00 |
|
|
|
cebca698e2
|
[Qwen3.8] Enable NVIDIA NVFP4 on DGX Spark with file-backed PLE and PDL router fix (#39126)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: rdxa <rdxa@rdxa-int-spark-01.yvb.moe>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Manrique <nanomlm@gmail.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
|
2026-09-13 16:23:41 +08:00 |
|
|
Thomas Wang
|
ec5fba5777
|
[AMD] Add dspark config and agentic workload section for deepseek-v4 model (#39252)
|
2026-09-12 19:32:01 -07:00 |
|
|
Xiaoyu ZhangandMick Qian
|
23bc4c6ed9
|
[Diffusion] Return Qwen-Image-Layered outputs and preserve CFG2 rounding (#38549)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-13 09:15:47 +08:00 |
|
|
Zhang, Jiejing
|
288627e400
|
[AMD] Document GLM-5.2 MXFP4 recipe update on MI355X (#39230)
|
2026-09-12 15:57:15 -07:00 |
|
|
Xinyuan Tong
|
b5a2aebc7e
|
[Docs] GLM-5.3-Flash cookbook: fixed MTP 5/1/6, EP1 + flashinfer_trtllm on Blackwell (#39213)
|
2026-09-12 12:56:57 -07:00 |
|
|
desmond-intel
|
6dc7b3421b
|
Inference Support Mamba 2 and 1 (#34556)
|
2026-09-12 20:51:18 +08:00 |
|
|
ChangLiu0709
|
7bc4eb3740
|
[AMD] Update MI355X MXFP4 HiCache defaults and quick-reduce quantization for Qwen3.5 cookbook (#39104)
|
2026-09-12 00:59:32 -07:00 |
|
|
Khoa PhamandClaude Fable 5.1
|
6ba96d329f
|
[DCP] Resolve --dcp-comm-backend to fi_a2a/a2a by default for every model (#39165)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-11 23:48:42 -07:00 |
|
|
Khoa PhamandClaude Fable 5.1
|
0d08668821
|
[Cookbook] Kimi-K3: keep DCP under HiCache L1+L2 with DSPARK (#39190)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-11 23:14:24 -07:00 |
|
|
|
ff1ce11348
|
[diffusion] model: support VDN-H3 with a hybrid_window_attn_h3 backend (#37903)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Haocheng Xi <xihc@berkeley.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-09-12 11:36:32 +08:00 |
|
|
Vignesh Sethuraman
|
0d1bea77da
|
[AMD] Allow aiter attention backend for Gemma-4 (#38758)
|
2026-09-11 18:48:26 -07:00 |
|
|
Kevin Mi
|
5f3606c7b2
|
[Cookbook][AMD] Kimi-K3 MI350X/MI355X: pin a ROCm image with the DSPARK graph-capture fix, add measured cell numbers (#39029)
|
2026-09-11 16:10:44 -07:00 |
|
|
|
df6424967a
|
[docs] Add the NVIDIA NVFP4 export to the Qwen3.8-27B cookbook (#38611)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Jiminator <jimmysh341@gmail.com>
Co-authored-by: Jimmy Shong <69131491+Jiminator@users.noreply.github.com>
|
2026-09-11 11:58:30 -07:00 |
|
|
Zhang, Jiejing
|
d7c284b894
|
[AMD] Use the triton DSA backend for GLM-5.2 MXFP4 on MI355X (#39106)
|
2026-09-11 11:48:50 -07:00 |
|
|
MickandMick Qian
|
e016de462c
|
[diffusion] CI: expose nightly server telemetry coverage (#38782)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-11 23:07:37 +08:00 |
|
|
Siju Samuel
|
67d3a2ea57
|
[XPU] Make checkpoint_engine worker device-agnostic (#32382)
|
2026-09-11 09:56:39 +08:00 |
|
|
Mohammad Miadh AngkadandMohammad Angkad
|
52c191da52
|
[Deps] Retire the CUDA 12 lane (#38404)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
|
2026-09-10 16:58:09 -07:00 |
|
|
sglang-botandsglang-bot
|
887c401e15
|
docs: sync LMSYS SGLang blog cards (#36773)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
|
2026-09-10 18:37:14 +00:00 |
|
|
zijiexiaandClaude Opus 5
|
4b7331fb77
|
Make the remaining DeepSeek-V4.1 NVIDIA cells start (#38861)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-10 11:04:53 -07:00 |
|
|
Yuhao YangandClaude Code
|
a37ded1693
|
[Cookbook] DeepSeek-V4.1: add the HiCache L2 knob to the Playground (#38844)
Co-authored-by: Claude Code <noreply@anthropic.com>
|
2026-09-10 18:20:34 +08:00 |
|
|
MickandMick Qian
|
c9c26d56b2
|
[diffusion] docs: sync snapshot and minimax-h3 subblock features (#38784)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-10 17:23:43 +08:00 |
|
|
zijiexiaandClaude Opus 5
|
5caafd2118
|
Fix the DeepSeek-V4.1 reasoning example and mark the B300 cells verified (#38839)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-10 01:49:44 -07:00 |
|
|
Xinyuan Tong
|
9a2f17f41d
|
Add INT4 and FP4 lanes to the Ling-3.0-flash-VL cookbook (#38527)
|
2026-09-10 15:23:50 +08:00 |
|
|
|
1b77f498a0
|
[NVIDIA] Support flashinfer Mega Moe (#31470)
Co-authored-by: djns99 <40156487+djns99@users.noreply.github.com>
Co-authored-by: 云挚 <ningyunxiao.nyx@antgroup.com>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
|
2026-09-10 00:22:47 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
c0b790cf7f
|
Delete cutlass_mla, non-Marlin GPTQ, AWQ AOT kernel, and Dual Chunk Flash Attention (#32114)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-09-10 15:12:01 +08:00 |
|
|
zijiexiaandClaude Opus 5
|
69777c4d36
|
Add DeepSeek-V4.1 Flash cookbook (#38802)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-09 23:15:30 -07:00 |
|
|
Thomas Wang
|
c415f977b8
|
[AMD] Update v4 args for agentic workload (#38677)
|
2026-09-09 21:41:05 -07:00 |
|
|
MickandMick Qian
|
ce555ed82a
|
[diffusion] refactor: refactor utility ownership and document helper placement (#38699)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-10 09:11:01 +08:00 |
|
|
Alison Shao
|
a7e00b7576
|
[CI] Answer unrecognized slash commands instead of skipping silently (#38736)
|
2026-09-09 18:01:18 -07:00 |
|
|
William Hu
|
0084030179
|
Add Opt-In for GLM-5.3 Flash breakable prefill CUDA graphs (#38522)
|
2026-09-09 17:02:08 -07:00 |
|
|
Alison Shao
|
2948a62a6f
|
[CI] Add /run-full-ci and /run-extra-ci slash commands (#38734)
|
2026-09-09 13:56:38 -07:00 |
|
|
Even Zhou
|
dba34cc964
|
[NPU] Bump memfabric and sgl-kernel-npu versions in docs and pyproject_npu.toml (#38437)
|
2026-09-09 19:53:49 +08:00 |
|